2020 · 62 citations · 36 references
EngineeringEvasion TechniqueInformation SecurityBiometricsSide-channel AttackAutomatic Speaker VerificationSpeech RecognitionSpeaker IdentificationSpeaker DiarizationNetwork SecurityHealth SciencesDefense MechanismsIdentity-based SecurityWeakest PartsComputer ScienceData SecurityCryptographyAttack ModelSpeech ProcessingSpeaker Recognition
Security of automatic speaker verification (ASV) systems is compromised by various spoofing attacks.While many types of non-proactive attacks (and their defenses) have been studied in the past, attacker's perspective on ASV, represents a far less explored direction.It can potentially help to identify the weakest parts of ASV systems and be used to develop attackeraware systems.We present an overview on this emerging research area by focusing on potential threats of adversarial attacks on ASV, spoofing countermeasures, or both.We conclude the study with discussion on selected attacks and leveraging from such knowledge to improve defense mechanisms against adversarial attacks.
36
Intriguing properties of neural networks
Christian Szegedy, Wojciech Zaremba, Ilya Sutskever et al. · arXiv (Cornell University) · 2013 · 5.7K citations · Full text
Artificial Intelligence, Geometric Learning, Convolutional Neural Network +14
Practical Black-Box Attacks against Machine Learning
Nicolas Papernot, Patrick McDaniel, Ian Goodfellow et al. · 2017 · 3.4K citations
Artificial Intelligence, Deep Neural Networks, Engineering +13
Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks
Weilin Xu, David Evans, Yanjun Qi · 2018 · 1.8K citations · Full text